Automatic Face Image Analysis
Project funded by own resources
Project title Automatic Face Image Analysis
Principal Investigator(s) Vetter, Thomas
Project Members Schönborn, Sandro
Morel, Andreas
Egger, Bernhard
Schneider, Andreas
Organisation / Research unit Departement Mathematik und Informatik / Computergraphik Bilderkennung (Vetter)
Project start 01.01.2008
Probable end 31.12.2018
Status Active
Abstract

We use the 3DMM to analyze images of human faces in an Analysis-by-Synthesis manner. The model is used to actively reconstruct the 3D shape of the depicted faces from a single image. This analysis task is one of the main applications of the Morphable Model of faces since the beginning. But so far, the analysis needed manual user intervention to initialize the model appropriately. An automatic initialization is possible using face and feature point detection technology but it has always been unreliable for non-frontal faces. In this project focus, we develop detection methods which can deal with non-frontal situations. To deal with unreliable input information, we directly integrate detection information into our probabilistic Markov Chain Monte Carlo model fitting method. The method is based on a propose-and-verify architecture which can deal with unreliable information by separating proposals from their verification with the generative model.

Financed by University funds
Other funds

Published results ()

  ID Autor(en) Titel ISSN / ISBN Erschienen in Art der Publikation
110087  Paysan, Pascal; Knothe, Reinhard; Amberg, Brian; Romdhani, Sami; Vetter, Thomas  A 3D Face Model for Pose and Illumination Invariant Face Recognition      Publication: ConferencePaper (Artikel, die in Tagungsbänden erschienen sind) 
2315088  Zivanov, Jasenko; Forster, Andreas; Schoenborn, Sandro; Vetter, Thomas  Human face shape analysis under spherical harmonics illumination considering self occlusion      Publication: ConferencePaper (Artikel, die in Tagungsbänden erschienen sind) 
2332543  Schönborn, Sandro; Forster, Andreas; Egger, Bernhard; Vetter, Thomas  A Monte Carlo strategy to integrate detection and model-based face analysis  978-3-642-40601-0  Pattern recognition, 35th German conference, GCPR 2013  Publication: Book Item (Buchkap., Lexikonartikel, jur. Kommentierung, Beiträge in Sammelbänden etc.) 
   

MCSS v5.8 PRO. 1.067 sec, queries - 0.000 sec ©Universität Basel  |  Impressum   |    
20/10/2018